[ET-VK][ez] Fix registration for convolution operator #13227
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
## Context Update the registration of the convolution operator to indicate that the weight tensor is prepacked and should not undergo normal texture limits checking. The current registration may cause valid convolution operators to not be partitioned since the export logic will think the weight tensor is non representable using channels packed textures. An example weight size would be something like [256, 256, 1, 1] which would result in a texture with extents [1, 1, 16384] which may exceed texture limits on some machines. Differential Revision: [D79893086](https://our.internmc.facebook.com/intern/diff/D79893086/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13227
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 1 Unrelated FailureAs of commit 95eaebb with merge base 0f70a5d ( NEW FAILURES - The following jobs have failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
SS-JIA
added a commit
that referenced
this pull request
Aug 8, 2025
## Context Update the registration of the convolution operator to indicate that the weight tensor is prepacked and should not undergo normal texture limits checking. The current registration may cause valid convolution operators to not be partitioned since the export logic will think the weight tensor is non representable using channels packed textures. An example weight size would be something like [256, 256, 1, 1] which would result in a texture with extents [1, 1, 16384] which may exceed texture limits on some machines. Differential Revision: [D79893086](https://our.internmc.facebook.com/intern/diff/D79893086/) ghstack-source-id: 301689714 Pull Request resolved: #13227
meta-cla
bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D79893086 |
This PR needs a
|
trivedivivek
approved these changes
Aug 8, 2025
## Context Update the registration of the convolution operator to indicate that the weight tensor is prepacked and should not undergo normal texture limits checking. The current registration may cause valid convolution operators to not be partitioned since the export logic will think the weight tensor is non representable using channels packed textures. An example weight size would be something like [256, 256, 1, 1] which would result in a texture with extents [1, 1, 16384] which may exceed texture limits on some machines. Differential Revision: [D79893086](https://our.internmc.facebook.com/intern/diff/D79893086/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Aug 8, 2025
Pull Request resolved: #13227 ## Context Update the registration of the convolution operator to indicate that the weight tensor is prepacked and should not undergo normal texture limits checking. The current registration may cause valid convolution operators to not be partitioned since the export logic will think the weight tensor is non representable using channels packed textures. An example weight size would be something like [256, 256, 1, 1] which would result in a texture with extents [1, 1, 16384] which may exceed texture limits on some machines. Differential Revision: [D79893086](https://our.internmc.facebook.com/intern/diff/D79893086/) ghstack-source-id: 301766081
|
This pull request was exported from Phabricator. Differential Revision: D79893086 |
facebook-github-bot
merged commit 6a927f9
into
gh/SS-JIA/274/base
99 of 104 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
aten.cat.defaultto handle any number of input tensors #13226Context
Update the registration of the convolution operator to indicate that the weight tensor is prepacked and should not undergo normal texture limits checking. The current registration may cause valid convolution operators to not be partitioned since the export logic will think the weight tensor is non representable using channels packed textures. An example weight size would be something like [256, 256, 1, 1] which would result in a texture with extents [1, 1, 16384] which may exceed texture limits on some machines.
Differential Revision: D79893086